© 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. 13708
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and situations, specifically focusing on the word "arrests."

    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
    325
    +0.15
    0.6%
    1137
    +0.13
    0.5%
    1872
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.15
    0.05
    1872
    +0.13
    0.04
    1137
    +0.13
    0.04
    Negative Logits
    <bos>
    -0.55
    XMLSchema
    -0.53
    abetes
    -0.52
    эффици
    -0.50
     kaynağından
    -0.50
    contentLoaded
    -0.50
     ชุด
    -0.50
    remadura
    -0.49
    щему
    -0.49
     בכ
    -0.49
    POSITIVE LOGITS
     dises
    1.27
     mef
    1.26
     !...
    1.25
     ardu
    1.23
     ?...
    1.22
     milano
    1.22
     marseille
    1.21
     embra
    1.21
     thut
    1.18
     fta
    1.17
    Activations Density 0.172%

    No Known Activations