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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7866
    Prev
    Next
    INDEX
    Explanations

    the phrase "ready to go" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.48
    2.0%
    411
    +0.11
    0.5%
    1967
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.48
    0.06
    411
    +0.11
    0.04
    1334
    +0.10
    0.04
    Negative Logits
     intersper
    -0.90
     kask
    -0.68
     koz
    -0.67
     thut
    -0.66
     rouse
    -0.66
     Messieurs
    -0.65
     vierge
    -0.65
     forbear
    -0.64
     Lég
    -0.64
     fers
    -0.64
    POSITIVE LOGITS
    Să
    0.75
    Saluti
    0.74
    სქოლიო
    0.74
    Abraços
    0.72
    mutlich
    0.71
    wieś
    0.70
    según
    0.69
    Rispondi
    0.69
    település
    0.69
    Rozmiar
    0.69
    Activations Density 0.201%

    No Known Activations