© 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. 11245
    Prev
    Next
    INDEX
    Explanations

    mentions of academic research projects and related details

    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
    1842
    +0.21
    0.7%
    50
    +0.20
    0.7%
    1343
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.21
    0.10
    752
    +0.20
    0.06
    50
    +0.18
    0.07
    Negative Logits
     follic
    -0.59
     hozz
    -0.56
     tört
    -0.52
     therefore
    -0.52
    ,
    -0.51
     accordingly
    -0.51
     indeed
    -0.51
     chłop
    -0.50
     lenne
    -0.50
     coarsely
    -0.49
    POSITIVE LOGITS
     Cfr
    1.14
     lele
    1.13
     susun
    1.12
     meis
    1.10
     saar
    1.09
     BIBSYS
    1.09
     Hæ
    1.08
     palab
    1.05
     Juf
    1.05
     redé
    1.05
    Activations Density 0.648%

    No Known Activations