© 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. 14448
    Prev
    Next
    INDEX
    Explanations

    mentions of legal processes or proceedings

    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
    1385
    +0.09
    0.2%
    1013
    +0.09
    0.2%
    1048
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.09
    0.07
    2044
    +0.09
    0.07
    1071
    +0.07
    0.06
    Negative Logits
     aen
    -1.60
     encomp
    -1.58
     volunte
    -1.56
     fuf
    -1.55
     fta
    -1.53
     guarante
    -1.52
     inev
    -1.51
     reluct
    -1.51
     increa
    -1.50
     fte
    -1.50
    POSITIVE LOGITS
     considerably
    0.64
    parseColor
    0.63
    naphthal
    0.62
     significantly
    0.59
     onBind
    0.59
     forever
    0.58
     but
    0.58
     while
    0.58
    ].(
    0.57
     whereas
    0.57
    Activations Density 0.588%

    No Known Activations