© 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. 13061
    Prev
    Next
    INDEX
    Explanations

    details of accidents or critical medical conditions involving public figures

    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
    1150
    +0.13
    0.4%
    648
    +0.11
    0.3%
    2034
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.13
    0.06
    440
    +0.11
    0.05
    1694
    +0.10
    0.05
    Negative Logits
    você
    -0.82
    muito
    -0.81
     Outros
    -0.79
     Qualquer
    -0.77
    excelente
    -0.76
     Queste
    -0.76
     Infatti
    -0.75
    Será
    -0.74
    Cześć
    -0.74
     Ciò
    -0.74
    POSITIVE LOGITS
    ↵↵↵
    0.54
     ‏
    0.53
    ↵↵
    0.50
    ↵
    0.49
    ↵↵↵↵
    0.48
     Emilie
    0.48
    .
    0.48
     -
    0.48
    umblr
    0.48
    <bos>
    0.47
    Activations Density 0.098%

    No Known Activations