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. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 61081
    Prev
    Next
    INDEX
    Explanations

    references to error messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     message
    -1.18
    ]")]
    -0.75
    }`).
    -0.73
     voice
    -0.71
     Мексичка
    -0.67
    })));
    -0.66
    >');
    -0.66
    message
    -0.66
    MigrationBuilder
    -0.66
     dedication
    -0.65
    POSITIVE LOGITS
    DIPSETTING
    0.53
     equivalently
    0.50
     congen
    0.49
    ależ
    0.49
     Früh
    0.49
    MEMBER
    0.49
    ,
    0.49
    chafter
    0.48
    Notes
    0.48
     Notes
    0.47
    Activations Density 0.029%

    No Known Activations