© 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. 14085
    Prev
    Next
    INDEX
    Explanations

    changes or updates in software applications, specifically focusing on bug fixes and new features

    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
    1871
    +0.21
    0.7%
    2019
    +0.20
    0.7%
    1553
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.21
    0.04
    1553
    +0.20
    0.04
    924
    +0.16
    0.04
    Negative Logits
     unspeak
    -0.98
     murmuring
    -0.96
     mischie
    -0.93
     mirth
    -0.92
     quivering
    -0.89
     moaning
    -0.88
     merrily
    -0.88
     hurrying
    -0.88
     talkin
    -0.86
     wavering
    -0.86
    POSITIVE LOGITS
     illustre
    1.46
     mikrofon
    1.44
     maniere
    1.42
     karton
    1.39
    🕗
    1.35
     kosme
    1.31
     balkon
    1.28
     Konkur
    1.27
    ..\..\
    1.24
     bunda
    1.24
    Activations Density 0.182%

    No Known Activations