© 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. 1041
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to the appearance or texture of objects

    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
    1328
    +0.18
    0.7%
    481
    +0.12
    0.5%
    479
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.18
    0.02
    481
    +0.12
    0.02
    438
    +0.10
    0.02
    Negative Logits
     unce
    -0.76
     vainly
    -0.64
     Punj
    -0.63
     myst
    -0.63
     kef
    -0.63
     purcha
    -0.62
     collier
    -0.62
     isolato
    -0.62
     Keny
    -0.62
     panama
    -0.61
    POSITIVE LOGITS
    flat
    1.40
     flat
    1.38
    Flat
    1.30
     Flat
    1.28
     FLAT
    1.07
     flats
    1.05
    FLAT
    1.05
    flatten
    0.85
    flats
    0.81
     Flats
    0.80
    Activations Density 0.072%

    No Known Activations