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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2688
    Prev
    Next
    INDEX
    Explanations

    measurements, statistics, and technical details related to weaponry or military equipment

    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
    1035
    +0.13
    0.4%
    553
    +0.12
    0.4%
    667
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1527
    +0.13
    0.04
    553
    +0.12
    0.05
    382
    +0.10
    0.05
    Negative Logits
    født
    -0.58
    Créditos
    -0.53
    ఔ
    -0.50
    destroyAll
    -0.48
     geldig
    -0.48
     sobald
    -0.46
    spesies
    -0.46
    Če
    -0.46
    Contours
    -0.45
     calculées
    -0.45
    POSITIVE LOGITS
     javier
    1.07
     suscep
    1.03
     fernando
    1.01
     aen
    1.00
     jacques
    1.00
     nicolas
    0.99
     reluct
    0.99
     yves
    0.99
     !...
    0.97
     affor
    0.97
    Activations Density 0.228%

    No Known Activations