© 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. 2371
    Prev
    Next
    INDEX
    Explanations

    the word "brand" with various contexts and focus points

    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
    553
    +0.23
    0.9%
    1870
    +0.13
    0.5%
    405
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.23
    0.05
    1708
    +0.13
    0.02
    405
    +0.12
    0.02
    Negative Logits
    İstinadlar
    -0.50
    toObject
    -0.48
     jaro
    -0.47
    Décès
    -0.46
    xhttp
    -0.45
     Futter
    -0.43
     canlynol
    -0.43
    RTHOOK
    -0.43
     hek
    -0.43
    centage
    -0.42
    POSITIVE LOGITS
    brand
    1.30
     brand
    1.29
     BRAND
    1.25
     Brand
    1.24
    Brand
    1.22
    BRAND
    1.18
     brands
    1.15
    brands
    1.13
    Brands
    1.11
    Branding
    1.09
    Activations Density 0.056%

    No Known Activations