© 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. 2541
    Prev
    Next
    INDEX
    Explanations

    negative events or situations involving legal consequences, especially in relation to criminal activities

    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
    1741
    +0.20
    0.7%
    50
    +0.16
    0.5%
    1967
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.20
    0.07
    1967
    +0.16
    0.05
    50
    +0.16
    0.05
    Negative Logits
     monstre
    -0.87
     madonna
    -0.85
     vété
    -0.85
     pegasus
    -0.83
     tremb
    -0.83
     milf
    -0.82
     gardien
    -0.81
     yoda
    -0.81
     outlander
    -0.80
     !...
    -0.79
    POSITIVE LOGITS
    ഉ
    0.64
    ñadir
    0.62
    Már
    0.61
    Eksteraj
    0.58
     entire
    0.57
     Cár
    0.57
    ἀ
    0.56
    Serviço
    0.56
    És
    0.55
    Aceite
    0.55
    Activations Density 0.307%

    No Known Activations