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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7209
    Prev
    Next
    INDEX
    Explanations

    the word "back", phrases using the word "together", the words "motion picture", and references to award ceremonies.

    oai_token-act-pair · gemini-2.0-flash

    coming back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.63
    RepeatedField
    -0.62
    ofus
    -0.57
    }],
    
    -0.57
    :])
    -0.56
     Roskov
    -0.56
    })]
    -0.56
    }]
    
    -0.56
    aws
    -0.55
    wikidata
    -0.55
    POSITIVE LOGITS
    <bos>
    1.38
     wikipagina
    0.68
    достатки
    0.57
     <>",
    0.56
    berdayakan
    0.56
    Filmo
    0.56
     disant
    0.55
     Wicidata
    0.54
     vectorielle
    0.53
     kysy
    0.53
    Activations Density 0.394%

    No Known Activations