Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1565
    Prev
    Next
    INDEX
    Explanations

    descriptions of historical events, locations, and fatalities

    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
    674
    +0.10
    0.3%
    459
    +0.08
    0.2%
    1314
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1820
    +0.10
    0.03
    7
    +0.08
    0.03
    3
    +0.08
    0.03
    Negative Logits
     Simult
    -0.99
     seiz
    -0.90
     Hano
    -0.88
     Manufact
    -0.88
     reluct
    -0.86
     unan
    -0.86
     Voi
    -0.86
     Arro
    -0.83
     Langu
    -0.83
     Epif
    -0.83
    POSITIVE LOGITS
    <bos>
    0.99
     invokingState
    0.56
     trajets
    0.55
     around
    0.53
    or
    0.53
    USTAIN
    0.53
    Trọng
    0.53
    diğini
    0.52
     ModelExpression
    0.51
    ValueStyle
    0.50
    Activations Density 0.102%

    No Known Activations