© 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. 13026
    Prev
    Next
    INDEX
    Explanations

    code snippets related to connecting or merging linked lists

    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
    876
    +0.28
    0.9%
    906
    +0.14
    0.4%
    1445
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.28
    0.00
    1511
    +0.14
    0.01
    474
    +0.12
    0.02
    Negative Logits
    <strong>
    -1.05
    <b>
    -1.03
    <em>
    -1.00
    <u>
    -0.98
    <i>
    -0.95
    .
    -0.95
    <eos>
    -0.94
    ,
    -0.89
    <blockquote>
    -0.89
    <sup>
    -0.89
    POSITIVE LOGITS
     increa
    3.51
     unden
    3.47
     affor
    3.39
     embra
    3.39
     desir
    3.39
     encomp
    3.38
     reluct
    3.38
     effe
    3.37
     intermitt
    3.35
     guarante
    3.33
    Activations Density 0.160%

    No Known Activations