© 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. 14615
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific sports team

    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
    506
    +0.17
    0.8%
    31
    +0.17
    0.8%
    896
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.17
    0.04
    1624
    +0.17
    0.04
    1177
    +0.16
    0.02
    Negative Logits
     panty
    -0.57
     callBack
    -0.57
     userType
    -0.56
     corduroy
    -0.56
     swarovski
    -0.56
     unlaw
    -0.55
    silicone
    -0.55
     Ribe
    -0.53
     affez
    -0.51
     cushi
    -0.51
    POSITIVE LOGITS
     Cincinnati
    0.86
    Cincinnati
    0.83
     Cin
    0.78
    Cin
    0.71
     Bengals
    0.70
     CIN
    0.59
     cinnamon
    0.58
    CIN
    0.58
     Mila
    0.56
     Cinnamon
    0.56
    Activations Density 0.311%

    No Known Activations