© 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. 7678
    Prev
    Next
    INDEX
    Explanations

    sections related to philosophical concepts and environmental issues

    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
    260
    +0.08
    0.2%
    814
    +0.08
    0.2%
    227
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.08
    0.03
    1088
    +0.08
    0.04
    1997
    +0.08
    0.03
    Negative Logits
     guarante
    -1.39
     volunte
    -1.34
     accla
    -1.32
     wherea
    -1.30
     inev
    -1.29
     impractica
    -1.28
     encomp
    -1.28
     reluct
    -1.27
     philanth
    -1.26
     perfon
    -1.26
    POSITIVE LOGITS
    <bos>
    0.95
    ,
    0.65
    AsUp
    0.62
    Havolalar
    0.61
     فإن
    0.61
     aDecoder
    0.59
    RenderAtEndOf
    0.58
    tanleria
    0.58
    رشف
    0.58
    ResponseWriter
    0.57
    Activations Density 0.135%

    No Known Activations