© 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. 24-GEMMASCOPE-RES-16K
    11. 12582
    Prev
    Next
    INDEX
    Explanations

    computer programming terms and syntax used in code, particularly in the context of object-oriented programming and memory management

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

    Hexadecimal codes and numbers

    np_acts-logits-general · gemini-2.0-flash

    names and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )"),
    -1.62
    "]),
    -1.41
    ,’”
    -1.40
    ']],
    -1.37
    ')),
    -1.37
    '));
    -1.36
    )");
    -1.36
    ")),
    -1.35
    !")
    -1.33
    '),
    -1.33
    POSITIVE LOGITS
    ),
    0.69
    Aholisi
    0.63
     TextInputType
    0.58
    },
    0.58
    ########.
    0.53
    viewBox
    0.52
     FetchType
    0.52
    ườn
    0.52
    बाह
    0.51
     NSCoder
    0.49
    Activations Density 0.636%

    No Known Activations