© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    complex scenarios involving legal issues and personal challenges

    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
    1978
    +0.11
    0.3%
    674
    +0.10
    0.3%
    69
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.11
    0.02
    658
    +0.10
    0.06
    2044
    +0.09
    0.06
    Negative Logits
     erec
    -0.92
     Cfr
    -0.88
     kani
    -0.87
     sappi
    -0.86
     Keny
    -0.85
     dises
    -0.85
     ivi
    -0.85
     umo
    -0.85
     lidl
    -0.83
     levis
    -0.82
    POSITIVE LOGITS
     yourself
    1.06
    yourself
    0.94
     you
    0.90
     your
    0.88
    your
    0.81
    you
    0.79
     You
    0.76
     yourselves
    0.75
     Yourself
    0.75
    You
    0.73
    Activations Density 0.488%

    No Known Activations