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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5681
    Prev
    Next
    INDEX
    Explanations

    terms related to visual and graphic content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    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
    }))
    
    -0.56
    })->
    -0.55
     })}
    -0.54
    ")));
    
    -0.54
    }}/>
    -0.54
     []);
    -0.53
    })]
    -0.52
    }])
    -0.52
    //});
    -0.52
    POSITIVE LOGITS
    tic
    1.04
    ic
    0.95
    tics
    0.93
    gic
    0.85
    atic
    0.85
    thic
    0.85
    isic
    0.84
    OTIC
    0.83
    betic
    0.83
    lic
    0.83
    Activations Density 0.491%

    No Known Activations