© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5697
    Prev
    Next
    INDEX
    Explanations

    references to baseball players and their statistics

    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
    1577
    +0.33
    1.2%
    137
    +0.19
    0.7%
    1842
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.33
    0.23
    184
    +0.19
    0.01
    1842
    +0.18
    0.14
    Negative Logits
     pymysql
    -1.17
     Messieurs
    -1.08
     ftill
    -1.00
     suspic
    -0.99
     madonna
    -0.95
     ftre
    -0.95
     paillettes
    -0.94
     Mlle
    -0.93
     fays
    -0.93
     fince
    -0.92
    POSITIVE LOGITS
     
    0.46
    </b>
    0.44
    }.
    0.43
    ↵↵
    0.42
    Зноскі
    0.42
    Stk
    0.41
    —
    0.41
    .
    0.41
    ..
    0.41
    ...
    0.40
    Activations Density 9.079%

    No Known Activations