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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6025
    Prev
    Next
    INDEX
    Explanations

    opening and closing curly braces in code structures

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

    opening braces `{` that mark the start of code blocks or method/class bodies.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ----</
    -0.55
     HttpNotFound
    -0.50
     Wikiseite
    -0.49
    Groeten
    -0.48
    AnchorStyles
    -0.47
    StoryboardSegue
    -0.46
     volunteers
    -0.46
     Hermans
    -0.45
     wikipagina
    -0.43
     Gould
    -0.43
    POSITIVE LOGITS
     }
    0.47
    httphttps
    0.47
    ...}
    0.46
    ükemmel
    0.45
    ""}
    0.44
    ;}
    0.41
    цездатний
    0.40
    ?}
    0.40
     }
    
    0.39
    }}}
    
    0.38
    Activations Density 0.213%

    No Known Activations