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. 6-RES-JB
    6. 9043
    Prev
    Next
    INDEX
    Explanations

    locations and landmarks in the countryside

    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
    976
    +0.13
    0.6%
    220
    +0.13
    0.6%
    1023
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.13
    0.09
    227
    +0.13
    0.09
    203
    +0.12
    0.07
    Negative Logits
    <bos>
    -1.93
     nahilalakip
    -0.81
    AnchorStyles
    -0.80
    execSQL
    -0.79
    oa̍t
    -0.78
    rrggbb
    -0.76
    Билгалдахарш
    -0.75
    Incluso
    -0.75
    Recuerda
    -0.75
    Legături
    -0.74
    POSITIVE LOGITS
     milf
    1.91
     shenan
    1.89
     indestru
    1.84
     maneu
    1.76
     ftu
    1.74
     increa
    1.72
     „,
    1.69
     madonna
    1.67
     depic
    1.64
     !...
    1.64
    Activations Density 0.648%

    No Known Activations