© 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. 13866
    Prev
    Next
    INDEX
    Explanations

    food recipes and associated details

    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
    1699
    +0.16
    0.5%
    906
    +0.14
    0.4%
    599
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.16
    0.07
    382
    +0.14
    0.06
    906
    +0.13
    -0.00
    Negative Logits
    astéro
    -0.75
    Wię
    -0.75
    więcej
    -0.73
    Și
    -0.72
    bardziej
    -0.72
    Ông
    -0.72
    Warto
    -0.70
    Jako
    -0.69
    distrito
    -0.69
    Galería
    -0.68
    POSITIVE LOGITS
     noel
    1.28
     lein
    1.26
     dispen
    1.22
     casio
    1.22
     profi
    1.21
     edp
    1.21
     mef
    1.21
     lara
    1.20
     afp
    1.20
     lele
    1.19
    Activations Density 0.702%

    No Known Activations