© 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. 14174
    Prev
    Next
    INDEX
    Explanations

    names of individuals and locations

    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
    1919
    +0.17
    0.5%
    1499
    +0.14
    0.4%
    1097
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.17
    0.07
    1097
    +0.14
    0.06
    888
    +0.11
    0.04
    Negative Logits
     thermomix
    -1.71
     bordeaux
    -1.60
     fluo
    -1.51
     matel
    -1.47
     frambo
    -1.38
     swarovski
    -1.38
     tricot
    -1.37
     soigne
    -1.36
     murano
    -1.36
     ibiza
    -1.35
    POSITIVE LOGITS
     said
    0.98
     also
    0.96
     says
    0.90
     explained
    0.86
     believes
    0.83
     spoke
    0.82
     noted
    0.82
     told
    0.82
     explains
    0.79
     suggests
    0.78
    Activations Density 0.181%

    No Known Activations