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. 4-GEMMASCOPE-RES-16K
    6. 602
    Prev
    Next
    INDEX
    Explanations

    C programming constructs and error reporting functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.60
     linh
    -0.49
    Xaml
    -0.47
     Ob
    -0.46
    sdp
    -0.45
    AutoScaleMode
    -0.45
    IntoConstraints
    -0.44
     Biôgrafia
    -0.44
     ob
    -0.44
     E
    -0.44
    POSITIVE LOGITS
    strcmp
    1.85
    strcpy
    1.76
     strcmp
    1.73
     strlen
    1.66
    strlen
    1.66
    memset
    1.53
    strncpy
    1.52
    strncmp
    1.46
    memcpy
    1.40
    memcmp
    1.38
    Activations Density 0.042%

    No Known Activations