© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13905
    Prev
    Next
    INDEX
    Explanations

    language related to requirements or needs

    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
    241
    +0.10
    0.3%
    1053
    +0.10
    0.3%
    1339
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.10
    0.03
    1103
    +0.10
    0.03
    1140
    +0.10
    0.03
    Negative Logits
     désigne
    -0.70
     prouve
    -0.56
     ferait
    -0.52
     apparaît
    -0.52
     trouvera
    -0.51
     protège
    -0.49
     reconnaît
    -0.49
     résulte
    -0.48
    printStats
    -0.48
    Truthy
    -0.48
    POSITIVE LOGITS
     require
    0.84
     requiring
    0.81
    require
    0.80
     Requires
    0.79
     Require
    0.77
     requires
    0.76
    Require
    0.71
    requires
    0.68
     REQUIRE
    0.67
    requireNonNull
    0.66
    Activations Density 0.069%

    No Known Activations