© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 1084
    Prev
    Next
    INDEX
    Explanations

    numerical values like prices and figures

    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
    1045
    +0.12
    0.4%
    976
    +0.10
    0.3%
    501
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    860
    +0.12
    0.04
    655
    +0.10
    0.04
    315
    +0.10
    0.04
    Negative Logits
    Elke
    -0.50
     supposes
    -0.47
     récente
    -0.47
     Aha
    -0.45
    Obr
    -0.45
     témoin
    -0.45
     enquired
    -0.42
     fidèle
    -0.42
     presupposes
    -0.42
     miscon
    -0.42
    POSITIVE LOGITS
    (">>
    0.65
     karton
    0.63
    dolu
    0.61
     Ainda
    0.61
     vogli
    0.61
    mbggenerated
    0.61
     maksi
    0.59
     Comunicação
    0.59
     Talvez
    0.59
     alkoh
    0.58
    Activations Density 0.086%

    No Known Activations