© 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. 990
    Prev
    Next
    INDEX
    Explanations

    statements related to government initiatives, policies, and technology advancements

    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
    381
    +0.12
    0.4%
    1919
    +0.11
    0.4%
    1262
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.10
    1415
    +0.11
    0.07
    805
    +0.09
    0.07
    Negative Logits
     ecru
    -1.50
     vété
    -1.46
     swarovski
    -1.45
     casio
    -1.42
     hcm
    -1.41
     squa
    -1.41
     inext
    -1.38
     stockholm
    -1.38
     oleo
    -1.35
     bordeaux
    -1.34
    POSITIVE LOGITS
     ourselves
    0.95
     we
    0.83
     We
    0.79
    We
    0.76
     have
    0.75
    we
    0.74
     our
    0.71
     hope
    0.70
     want
    0.67
     need
    0.67
    Activations Density 0.338%

    No Known Activations