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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2562
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific events or actions occurring at a particular location

    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
    61
    +0.11
    0.4%
    674
    +0.11
    0.4%
    251
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.11
    0.04
    1140
    +0.11
    0.05
    251
    +0.09
    0.04
    Negative Logits
     "}";
    -0.56
     насељу
    -0.55
     hydrat
    -0.54
    definecolor
    -0.53
    "}";
    -0.53
     للاسماء
    -0.53
     snippetHide
    -0.52
     "','
    -0.51
     "'");
    -0.50
     mily
    -0.49
    POSITIVE LOGITS
     TAKE
    1.07
    Takes
    1.06
     take
    1.03
     Takes
    1.00
    take
    0.99
    Took
    0.98
    takes
    0.97
    took
    0.95
     TAK
    0.94
     Take
    0.94
    Activations Density 0.111%

    No Known Activations