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. 18-GEMMASCOPE-RES-16K
    6. 3778
    Prev
    Next
    INDEX
    Explanations

    quotes and statements made by individuals

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

    Quotation after the word "said" or "says."

    np_acts-logits-general · gemini-2.0-flash

    reporting statements attributed to people

    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
    ScopeManager
    -0.60
     Jurí
    -0.57
    fastjson
    -0.56
    SizeMode
    -0.55
    +#+#
    -0.55
    npmjs
    -0.55
    kháu
    -0.55
     fallu
    -0.54
    featureID
    -0.54
     itself
    -0.53
    POSITIVE LOGITS
    ")));
    
    0.78
    ])).
    0.73
    '}),
    0.73
    })`
    0.72
    ++]=
    0.71
    ]]:
    0.69
    ])),
    0.67
    ),),
    0.67
    ))).
    0.66
    .")]
    0.65
    Activations Density 0.080%

    No Known Activations