Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15164
    Prev
    Next
    INDEX
    Explanations

    names of individuals or groups

    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
    50
    +0.20
    0.7%
    1577
    +0.19
    0.7%
    1177
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.20
    0.22
    1177
    +0.19
    0.11
    678
    +0.12
    0.15
    Negative Logits
    TagMode
    -0.92
    gdala
    -0.76
    archiviato
    -0.74
    wikidata
    -0.73
    anyahu
    -0.73
     onPostExecute
    -0.69
     자신의
    -0.68
    idopsis
    -0.67
    rinology
    -0.67
    ="#"><
    -0.67
    POSITIVE LOGITS
     emphat
    2.28
     inev
    2.28
     accla
    2.26
     effe
    2.25
     increa
    2.21
     wien
    2.21
     strick
    2.18
     mef
    2.17
     vhs
    2.16
     affor
    2.16
    Activations Density 3.267%

    No Known Activations