© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    descriptions of complex events or scenarios involving investigation and analysis

    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
    184
    +0.15
    0.4%
    1042
    +0.11
    0.3%
    872
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.02
    1965
    +0.11
    0.04
    1244
    +0.10
    0.02
    Negative Logits
     gend
    -0.84
     Gouver
    -0.83
     alkoh
    -0.80
     minimalis
    -0.80
     kosme
    -0.80
     kön
    -0.79
     kollek
    -0.78
     uefa
    -0.77
     praktik
    -0.77
     Khart
    -0.76
    POSITIVE LOGITS
    umably
    0.76
    raisemb
    0.73
     likely
    0.69
    rlrl
    0.69
     wouldn
    0.68
     would
    0.66
     surely
    0.66
    mutlich
    0.65
    wouldn
    0.63
     plausible
    0.61
    Activations Density 0.498%

    No Known Activations