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. 25-GEMMASCOPE-RES-16K
    6. 451
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to programming and data processing, particularly in the context of API usage and manipulating data streams

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

    references to data streaming and manipulation techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.69
    bibfield
    -0.53
     Secondo
    -0.52
     Cæsar
    -0.52
    İM
    -0.51
     Egli
    -0.50
     Económica
    -0.50
     colectiva
    -0.50
     Thine
    -0.50
    coeffs
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.61
    //
    0.50
    ]}$
    0.50
    }',
    0.50
    >(_
    0.50
    >'+
    0.49
    |}{}
    0.47
    )}$,
    0.47
     Bourgoin
    0.44
    }';
    0.44
    Activations Density 0.023%

    No Known Activations