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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 303
    Prev
    Next
    INDEX
    Explanations

    phrases related to branches, railways, and infrastructure

    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
    +0.14
    0.8%
    1407
    +0.12
    0.7%
    1331
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1026
    +0.14
    0.02
    1331
    +0.12
    0.01
    239
    +0.09
    0.02
    Negative Logits
    <bos>
    -3.09
    ⓧ
    -0.73
    public
    -0.69
    //---
    -0.68
    терак
    -0.64
    <?
    -0.64
    create
    -0.62
    Identyfik
    -0.61
    oredCriteria
    -0.61
    pub
    -0.60
    POSITIVE LOGITS
     ftu
    1.45
     stockholm
    1.41
     thut
    1.39
     vns
    1.36
     fta
    1.36
     milf
    1.35
     ftre
    1.35
     disagre
    1.35
     reft
    1.31
     unwarran
    1.31
    Activations Density 0.062%

    No Known Activations