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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12900
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions or events

    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
    964
    +0.17
    0.5%
    674
    +0.15
    0.4%
    906
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.17
    0.02
    838
    +0.15
    0.05
    2031
    +0.14
    0.04
    Negative Logits
     shenan
    -1.24
     tolerably
    -1.21
     indestru
    -1.19
     affor
    -1.17
     unspeak
    -1.16
     disagre
    -1.15
     reluct
    -1.15
     increa
    -1.13
     impra
    -1.11
     indescri
    -1.10
    POSITIVE LOGITS
    <bos>
    0.83
    المكان
    0.69
    Diweddarwch
    0.64
    Enllaços
    0.64
     Bourgoin
    0.63
     ujednoznacz
    0.63
     חיצוניים
    0.61
     Walkover
    0.61
     fieldNum
    0.61
     تانيه
    0.61
    Activations Density 0.934%

    No Known Activations