© 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. 18-GEMMASCOPE-RES-16K
    11. 8824
    Prev
    Next
    INDEX
    Explanations

    elements or phrases that involve parenthetical statements and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text within parentheses

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ).
    -1.41
    ].
    -1.34
    ».
    -1.31
    }.
    -1.25
    .
    -1.24
    。
    -1.22
    ".
    -1.19
    .
    -1.16
    }$.
    -1.11
    \}.
    -1.10
    POSITIVE LOGITS
     &___
    0.93
    rungsseite
    0.92
    WithMany
    0.89
    transQ
    0.88
     unknownFields
    0.86
    adaptiveStyles
    0.85
    IndentedString
    0.83
     ArrayAdapter
    0.81
    __(/*!
    0.81
    apunov
    0.81
    Activations Density 0.401%

    No Known Activations