Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8267
    Prev
    Next
    INDEX
    Explanations

    mentions of technology related to microchips or circuits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.14
    0.5%
    678
    +0.13
    0.5%
    144
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1602
    +0.14
    0.02
    144
    +0.13
    0.02
    406
    +0.13
    0.02
    Negative Logits
    GeoNames
    -0.51
    }}^
    -0.50
     at
    -0.49
    assertThrows
    -0.49
     Вт
    -0.48
     Шев
    -0.48
    候
    -0.48
    RTSN
    -0.47
    TargetException
    -0.47
     an
    -0.47
    POSITIVE LOGITS
     nece
    1.56
     thut
    1.46
     mikro
    1.38
     dises
    1.36
     effe
    1.36
     fta
    1.35
     foon
    1.33
     desir
    1.33
     makro
    1.32
     aen
    1.31
    Activations Density 0.043%

    No Known Activations