© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 1176
    Prev
    Next
    INDEX
    Explanations

    assessments of emotional experiences or challenges

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

    Follows prepositions or nouns

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']}
    -0.56
    出版年
    -0.54
    ']:
    -0.53
     }}}
    -0.53
     }))
    -0.53
    ☚
    -0.53
    '].'
    -0.52
    ASING
    -0.52
    })));
    -0.50
     }}
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    1.02
    yntaxException
    0.91
    脚注の使い方
    0.89
    parsedMessage
    0.85
    WithIOException
    0.81
    InitVars
    0.81
    AsUp
    0.77
    Diweddarwch
    0.77
    NameInMap
    0.76
    PerformLayout
    0.73
    Activations Density 0.444%

    No Known Activations