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. 0-RES-JB
    6. 193
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    871
    +0.06
    0.2%
    1877
    +0.06
    0.2%
    564
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.06
    0.02
    1343
    +0.06
    0.05
    1363
    +0.06
    0.04
    Negative Logits
     sophistic
    -1.24
     apprehen
    -1.17
     unspeak
    -1.11
     nobly
    -1.09
     vainly
    -1.02
     indescri
    -1.02
     disagre
    -1.02
     depic
    -1.01
     quitted
    -0.99
    
    
    -0.98
    POSITIVE LOGITS
    ken
    1.51
    brook
    1.42
    KEN
    0.97
    BROOK
    0.89
     tid
    0.84
    mberto
    0.80
     kule
    0.73
    keny
    0.72
     Amerik
    0.72
     splet
    0.69
    Activations Density 0.330%

    No Known Activations