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. 21-GEMMASCOPE-RES-16K
    6. 2058
    Prev
    Next
    INDEX
    Explanations

    programming assignment or operation outcomes involving variable assignments and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     +
    -0.46
    ]++;
    -0.44
    bootstrapcdn
    -0.44
     yes
    -0.44
    堆
    -0.44
    vski
    -0.43
     $+
    -0.43
    ríamos
    -0.42
    )+
    -0.42
    glEnable
    -0.42
    POSITIVE LOGITS
     false
    2.14
    false
    1.93
     False
    1.71
    False
    1.63
     FALSE
    1.45
    FALSE
    1.28
     falso
    1.12
     falsos
    1.12
     falsas
    1.09
     fausse
    1.08
    Activations Density 0.081%

    No Known Activations