Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1908
    Prev
    Next
    INDEX
    Explanations

    structured data formats and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -0.67
    ]]);
    -0.56
    ↵↵
    -0.55
    ↵↵↵↵
    -0.55
    ↵↵↵
    -0.55
    }
    -0.54
    ↵↵↵↵↵
    -0.50
    <eos>
    -0.50
    });
    -0.49
    })
    -0.48
    POSITIVE LOGITS
     disambiguazione
    0.84
    TextEditing
    0.76
    SequentialGroup
    0.75
     GenerationType
    0.74
     getItemId
    0.71
    onActivityResult
    0.66
    يميديا
    0.66
    GEBURTS
    0.66
     OnTrigger
    0.64
    esgue
    0.64
    Activations Density 0.033%

    No Known Activations