© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1029
    Prev
    Next
    INDEX
    Explanations

    programming structures and syntax elements related to C/C++ coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    randomUUID
    -0.61
    """.
    -0.56
     AspNetCore
    -0.55
     },
    -0.52
    },
    -0.51
    '][]
    -0.49
     Chiapas
    -0.49
     }</
    -0.49
     übers
    -0.48
     Simeon
    -0.47
    POSITIVE LOGITS
     ft
    1.01
    ft
    1.00
    ########.
    0.82
    :+:
    0.82
    libft
    0.76
    mlx
    0.65
    FT
    0.63
    Ft
    0.63
     FT
    0.58
     ſt
    0.58
    Activations Density 0.034%

    No Known Activations