© 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. 14614
    Prev
    Next
    INDEX
    Explanations

    mentions of legal laws or regulations, particularly those related to Islamic law and fatwas

    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
    1842
    +0.10
    0.3%
    1081
    +0.08
    0.2%
    1705
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.10
    0.05
    1705
    +0.08
    0.06
    1363
    +0.08
    0.05
    Negative Logits
     utop
    -0.71
     solidar
    -0.70
    //*/
    -0.66
     Divulgação
    -0.66
    (;;)
    -0.66
     ideolog
    -0.65
     republi
    -0.64
     recipro
    -0.64
     nomine
    -0.63
     Réalisation
    -0.63
    POSITIVE LOGITS
     (
    0.92
     unspeak
    0.84
     —
    0.81
    —
    0.78
     ("
    0.78
     horrend
    0.75
     (=
    0.73
     –
    0.73
     (“
    0.73
     meaning
    0.73
    Activations Density 0.561%

    No Known Activations