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. 5388
    Prev
    Next
    INDEX
    Explanations

    locations and related terms from the state of California

    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
    1757
    +0.18
    1.1%
    341
    +0.14
    0.8%
    404
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.18
    0.05
    395
    +0.14
    0.04
    438
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.24
    ⓧ
    -0.77
     intersper
    -0.71
     harmonize
    -0.69
     endow
    -0.65
     amass
    -0.64
     repress
    -0.63
     disarm
    -0.63
     disbur
    -0.60
    /**
    -0.60
    POSITIVE LOGITS
     CA
    1.20
     Kalifor
    1.04
    CA
    1.01
     kaos
    1.01
     California
    1.00
    California
    0.98
     Calif
    0.97
     california
    0.97
     CALIFORNIA
    0.93
     Mémoires
    0.90
    Activations Density 0.229%

    No Known Activations