Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7242
    Prev
    Next
    INDEX
    Explanations

    variable assignments involving 'self' and instances of the class structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Materiał
    -0.51
    <eos>
    -0.49
     investissements
    -0.47
     médicale
    -0.47
     indemnity
    -0.46
    "));
    -0.45
     régionale
    -0.45
    openSession
    -0.45
    paedic
    -0.45
     köl
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    UnusedPrivate
    0.78
     propOrder
    0.72
    PageRoute
    0.71
     unknownFields
    0.69
    ########.
    0.68
    PostInfinity
    0.66
    NSNotification
    0.66
    ModelAdmin
    0.65
     Reisedaten
    0.65
    Activations Density 0.036%

    No Known Activations