© 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. 12962
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and personal statements

    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
    1445
    +0.10
    0.3%
    270
    +0.07
    0.2%
    1218
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1068
    +0.10
    0.06
    32
    +0.07
    0.05
    702
    +0.07
    0.05
    Negative Logits
     umo
    -0.95
     lele
    -0.87
     pama
    -0.87
     hina
    -0.86
     lapto
    -0.83
     kuku
    -0.82
     mef
    -0.82
     gani
    -0.82
     kug
    -0.82
     huf
    -0.82
    POSITIVE LOGITS
     he
    0.70
     she
    0.60
     his
    0.58
     goodbye
    0.57
    she
    0.54
     they
    0.53
    <bos>
    0.52
     that
    0.48
     it
    0.48
     said
    0.48
    Activations Density 0.259%

    No Known Activations