© 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. 2414
    Prev
    Next
    INDEX
    Explanations

    commands or code snippets associated with a specific software or platform

    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
    410
    +0.20
    1.0%
    31
    +0.14
    0.7%
    421
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.20
    0.04
    981
    +0.14
    0.05
    227
    +0.13
    0.05
    Negative Logits
     nutella
    -0.70
     disreg
    -0.64
     uninten
    -0.61
     intersper
    -0.61
     Pyrene
    -0.59
     chrysler
    -0.59
     endeavored
    -0.59
     unspeak
    -0.58
     unve
    -0.58
     unlaw
    -0.58
    POSITIVE LOGITS
     CP
    1.13
     cp
    1.01
    CP
    1.00
    cp
    0.97
     Brooks
    0.97
    Brooks
    0.93
    Cp
    0.80
     BROOK
    0.79
     Brook
    0.76
     Cp
    0.72
    Activations Density 0.285%

    No Known Activations