© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 669
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically neighborhoods or areas within a city

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1046
    +0.07
    0.2%
    1473
    +0.07
    0.2%
    1992
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1046
    +0.07
    0.03
    968
    +0.07
    0.03
    1252
    +0.07
    0.03
    Negative Logits
     Tanja
    -0.76
     Malte
    -0.64
     Dign
    -0.64
     Winf
    -0.63
     Hannes
    -0.62
     demen
    -0.62
     Marcela
    -0.62
     MSR
    -0.62
     Katja
    -0.62
     Karsten
    -0.62
    POSITIVE LOGITS
     împre
    1.02
     sindaco
    0.97
     traffico
    0.95
     quartiere
    0.92
     cammino
    0.85
     carrefour
    0.84
     acoper
    0.83
     popoli
    0.81
     paradiso
    0.81
     depoz
    0.81
    Activations Density 0.278%

    No Known Activations