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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 122
    Prev
    Next
    INDEX
    Explanations

    symbols or markers indicating separation or pauses in text

    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
    +0.28
    1.0%
    2019
    +0.17
    0.7%
    752
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1990
    +0.28
    0.06
    2011
    +0.17
    0.05
    871
    +0.16
    0.05
    Negative Logits
    <bos>
    -1.45
     nadzie
    -0.92
    ,
    -0.88
    .
    -0.80
     and
    -0.79
     for
    -0.76
     in
    -0.76
     wspania
    -0.75
    和
    -0.74
     that
    -0.73
    POSITIVE LOGITS
     hcm
    1.76
     incess
    1.75
     allarg
    1.75
     Juf
    1.69
     volunte
    1.66
     nece
    1.63
     tramont
    1.59
     jaya
    1.59
     sappi
    1.58
     sovere
    1.57
    Activations Density 0.330%

    No Known Activations