© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 813
    Prev
    Next
    INDEX
    Explanations

    ranges of visibility or invisibility within rules and systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    871
    +0.14
    0.5%
    544
    +0.13
    0.5%
    481
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.02
    1047
    +0.13
    0.02
    1482
    +0.13
    0.02
    Negative Logits
     Bater
    -0.58
     Monark
    -0.54
     Quod
    -0.52
     Ibidem
    -0.50
     Teres
    -0.49
     Klagen
    -0.49
     Stefanie
    -0.49
     Musicians
    -0.48
     sputnik
    -0.48
     osal
    -0.48
    POSITIVE LOGITS
     visible
    1.07
    visible
    1.06
     visibility
    1.01
     Visible
    0.97
    Visible
    0.96
    VISIBLE
    0.91
    visibility
    0.88
     visibles
    0.88
     invisible
    0.86
     Visibility
    0.81
    Activations Density 0.092%

    No Known Activations