© 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. 14268
    Prev
    Next
    INDEX
    Explanations

    references to images or pictures within text

    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
    1942
    +0.13
    0.5%
    1983
    +0.13
    0.5%
    1218
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1942
    +0.13
    0.05
    1218
    +0.13
    0.04
    553
    +0.12
    0.04
    Negative Logits
    Törté
    -0.55
     xPos
    -0.54
    Bibliografie
    -0.53
    Fø
    -0.52
    Toponymie
    -0.52
    Kilder
    -0.50
    Nå
    -0.49
     automne
    -0.47
    Flere
    -0.47
    Referanser
    -0.47
    POSITIVE LOGITS
     image
    1.28
    image
    1.18
     Image
    1.17
     IMAGE
    1.10
    Image
    1.07
     images
    1.05
    IMAGE
    1.00
     Images
    0.93
    images
    0.87
     img
    0.87
    Activations Density 0.083%

    No Known Activations