© 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. 5690
    Prev
    Next
    INDEX
    Explanations

    information related to educational institutions and community programs

    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
    227
    +0.12
    0.4%
    1150
    +0.12
    0.3%
    872
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.07
    1657
    +0.12
    0.04
    324
    +0.11
    0.02
    Negative Logits
     dispen
    -1.34
     fte
    -1.28
     socie
    -1.24
     erec
    -1.23
     fep
    -1.21
     nece
    -1.20
     volunte
    -1.17
     ridu
    -1.16
     sovere
    -1.16
     desir
    -1.14
    POSITIVE LOGITS
     but
    0.68
     plus
    0.66
     into
    0.60
    เดิม
    0.59
     nhưng
    0.59
     existing
    0.59
    existing
    0.58
    original
    0.58
     original
    0.57
     with
    0.56
    Activations Density 0.571%

    No Known Activations