© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6216
    Prev
    Next
    INDEX
    Explanations

    passages related to writing, research, or discussions, particularly ones discussing questions, concepts, and analysis.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1967
    +0.22
    0.8%
    1577
    +0.22
    0.8%
    1150
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.22
    0.11
    16
    +0.22
    0.20
    1380
    +0.14
    0.01
    Negative Logits
     Kategor
    -0.63
     PLWABN
    -0.58
    TagMode
    -0.55
     getNome
    -0.54
     gela
    -0.52
     kompati
    -0.52
     kac
    -0.51
     kosme
    -0.51
     numerus
    -0.51
    BoxShadow
    -0.50
    POSITIVE LOGITS
     peasantry
    0.66
     disreg
    0.61
     embodi
    0.58
     philanth
    0.58
     ROBER
    0.58
     potentialities
    0.55
     practition
    0.54
     clergymen
    0.54
     prerog
    0.54
     impra
    0.54
    Activations Density 7.504%

    No Known Activations