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. 8-GEMMASCOPE-RES-16K
    6. 4814
    Prev
    Next
    INDEX
    Explanations

    sections of a document that indicate important notes or highlighted elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ğlık
    -0.72
    djangoproject
    -0.70
     GLC
    -0.60
    parsedMessage
    -0.58
    Szia
    -0.58
     الفلك
    -0.57
    Síguenos
    -0.57
     Etr
    -0.57
     newBuilder
    -0.56
    frastructure
    -0.55
    POSITIVE LOGITS
    *);
    0.81
    \#:
    0.81
    }:$
    0.80
    :✨
    0.79
    )]:
    0.77
    \":\"
    0.76
    //:
    0.76
    Tuk
    0.75
    ®:
    0.75
    ']:
    0.75
    Activations Density 0.008%

    No Known Activations