© 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. 4-GEMMASCOPE-RES-16K
    11. 881
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly in a mathematical or statistical context

    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
    دانشنامهٔ
    -1.07
    ]='\
    -0.98
    ']))
    -0.97
    ,:);
    -0.96
    ']],
    -0.95
    ]');
    -0.93
    ]]:
    -0.93
    }")
    -0.92
    <bos>
    -0.91
    ')],
    -0.90
    POSITIVE LOGITS
    2
    2.03
    3
    1.37
    4
    1.30
    1
    1.16
    0
    1.11
    5
    1.07
    6
    1.06
    8
    0.98
    7
    0.95
    nd
    0.90
    Activations Density 1.678%

    No Known Activations