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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 222
    Prev
    Next
    INDEX
    Explanations

    numerical values expressed as percentages or specific counts in a context related to data and reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.16
    0.5%
    1978
    +0.12
    0.4%
    382
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.16
    0.11
    776
    +0.12
    0.09
    382
    +0.07
    0.08
    Negative Logits
    <bos>
    -2.73
    /*---
    -0.63
     go
    -0.62
     li
    -0.60
     bir
    -0.58
    ⓧ
    -0.58
     protoimpl
    -0.57
     continue
    -0.56
    ///**
    -0.56
     reduce
    -0.56
    POSITIVE LOGITS
     lidl
    1.62
     stockholm
    1.61
     haup
    1.60
     increa
    1.59
     napoli
    1.58
     maneu
    1.58
     affor
    1.58
     impra
    1.55
     volunte
    1.51
     maroc
    1.47
    Activations Density 0.462%

    No Known Activations